spark-2.2.0-bin-hadoop2.6和spark-1.6.1-bin-hadoop2.6发行包自带案例全面详解（java、python、r和scala）之Basic包下的SparkTC.scala（图文详解）

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
//package org.apache.spark.examples
package zhouls.bigdata

import scala.util.Random
import scala.collection.mutable
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.SparkContext._



/**
 * Transitive closure on a graph.
 */
object SparkTC {
  
  val numEdges = 200
  val numVertices = 100
  val rand = new Random(42)

  def generateGraph: Seq[(Int, Int)] = {
    val edges: mutable.Set[(Int, Int)] = mutable.Set.empty
    while (edges.size < numEdges) {
      val from = rand.nextInt(numVertices)
      val to = rand.nextInt(numVertices)
      if (from != to) edges.+=((from, to))
    }
    edges.toSeq
  }

  
  /*
   * 主函数
   */
  def main(args: Array[String]) {
    val sparkConf = new SparkConf().setAppName("SparkTC").setMaster("local")
    val spark = new SparkContext(sparkConf)
    val slices = if (args.length > 0) args(0).toInt else 2
    var tc = spark.parallelize(generateGraph, slices).cache()

    // Linear transitive closure: each round grows paths by one edge,
    // by joining the graph's edges with the already-discovered paths.
    // e.g. join the path (y, z) from the TC with the edge (x, y) from
    // the graph to obtain the path (x, z).

    // Because join() joins on keys, the edges are stored in reversed order.
    val edges = tc.map(x => (x._2, x._1))//翻转起点和终点，方便join, (x,y) (y,z) ==>(x,z) 需要翻转(x,y)为（y,x）才能join出正确结果

    // This join is iterated until a fixed point is reached.（不断join，union并计算个数直到不变）
    var oldCount = 0L
    var nextCount = tc.count()
    do {
      oldCount = nextCount
      // Perform the join, obtaining an RDD of (y, (z, x)) pairs,
      // then project the result to obtain the new (x, z) paths.
      tc = tc.union(tc.join(edges).map(x => (x._2._2, x._2._1))).distinct().cache()
      nextCount = tc.count()
    } while (nextCount != oldCount)

    println("TC has " + tc.count() + " edges.")
    spark.stop()
  }
}
// scalastyle:on println

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 *
 *    http://www.apache.org/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

// scalastyle:off println
package org.apache.spark.examples

import scala.collection.mutable
import scala.util.Random
import org.apache.spark.sql.SparkSession

/**
 * Transitive closure on a graph.
 */
object SparkTC {
  
  val numEdges = 200
  val numVertices = 100
  val rand = new Random(42)

  /*
   * 1. 计算传递闭包（可到达路径数目）
     * 2. 自动生成图，使用可变Set存储起点，终点 
   */
  def generateGraph: Seq[(Int, Int)] = {
    val edges: mutable.Set[(Int, Int)] = mutable.Set.empty
    while (edges.size < numEdges) {
      val from = rand.nextInt(numVertices)
      val to = rand.nextInt(numVertices)
      if (from != to) edges.+=((from, to))
    }
    edges.toSeq
  }

  def main(args: Array[String]) {
    val spark = SparkSession
      .builder
      .master("local")
      .appName("SparkTC")
      .getOrCreate() 
      
    val slices = if (args.length > 0) args(0).toInt else 2
    var tc = spark.sparkContext.parallelize(generateGraph, slices).cache()

    // Linear transitive closure: each round grows paths by one edge,
    // by joining the graph's edges with the already-discovered paths.
    // e.g. join the path (y, z) from the TC with the edge (x, y) from
    // the graph to obtain the path (x, z).

    // Because join() joins on keys, the edges are stored in reversed order.
    val edges = tc.map(x => (x._2, x._1))//翻转起点和终点，方便join, (x,y) (y,z) ==>(x,z) 需要翻转(x,y)为（y,x）才能join出正确结果

    
    // This join is iterated until a fixed point is reached.（不断join，union并计算个数直到不变）
    var oldCount = 0L
    var nextCount = tc.count()
    do {
      oldCount = nextCount
      // Perform the join, obtaining an RDD of (y, (z, x)) pairs,
      // then project the result to obtain the new (x, z) paths.
      tc = tc.union(tc.join(edges).map(x => (x._2._2, x._2._1))).distinct().cache()
      nextCount = tc.count()
    } while (nextCount != oldCount)

    println("TC has " + tc.count() + " edges.")
    spark.stop()
  }
}
// scalastyle:on println